Asymptotic Poisson distribution for the number of system failures of a monotone system |
| |
Authors: | Terje Aven Harald Haukis |
| |
Affiliation: | Stavanger University College, Ullandhaug, 4004 Stavanger, Norway |
| |
Abstract: | It is well known that for highly available monotone systems, the time to the first system failure is approximately exponentially distributed. Various normalising factors can be used as the parameter of the exponential distribution to ensure the asymptotic exponentiality. More generally, it can be shown that the number of system failures is asymptotic Poisson distributed. In this paper we study the performance of some of the normalising factors by using Monte Carlo simulation. The results show that the exponential/Poisson distribution gives in general very good approximations for highly available components. The asymptotic failure rate of the system gives best results when the process is in steady state, whereas other normalising factors seem preferable when the process is not in steady state. From a computational point of view the asymptotic system failure rate is most attractive. |
| |
Keywords: | |
本文献已被 ScienceDirect 等数据库收录! |
|